INDEX

Explanations

moments of pausing or interruption in a narrative

oai_token-act-pair · gpt-3.5-turbo

references to pauses in speech or action

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gie

-0.68

NRS

-0.67

usted

-0.64

model

-0.63

MET

-0.62

ipped

-0.62

models

-0.61

Assembly

-0.61

ramid

-0.61

å¥³

-0.61

POSITIVE LOGITS

 pause

0.85

 pauses

0.83

gap

0.81

olicy

0.79

 paused

0.75

 disbelief

0.73

 moratorium

0.71

spection

0.71

 periods

0.71

 momentarily

0.70

Activations Density 0.047%

moments of pausing or interruption in a narrative

references to pauses in speech or action

No Comments

No Known Activations